Information processing system, information processing method, and program

Abstract

An information processing system includes: a selection part configured to select a speech recognition dictionary for use in speech recognition from among a plurality of speech recognition dictionaries; and a speech recognition part configured to generate speech recognition text by converting voices uttered during a voice call with a customer, into text, by speech recognition using the speech recognition dictionary selected by the selection part. In this information processing system, when a switchover to a different speech recognition dictionary selected is made by the selection part, the speech recognition part is configured to generate speech recognition text by converting voices uttered before the switchover is made, among the voices uttered during the voice call with the customer, into text, by speech recognition using the different speech recognition dictionary.

1 - 12 . (canceled) 
     
     
         13 . An information processing system comprising:
 a processor; and   a memory storing computer-executable instructions that, when executed by the processor, cause the information processing system to at least:
 select a first speech recognition dictionary for use in speech recognition from among a plurality of speech recognition dictionaries; 
 generate first speech recognition text by converting voices uttered during a voice call with a customer, into the first speech recognition text, by speech recognition using the first speech recognition dictionary; 
 select, subsequent to the selection of the first speech recognition dictionary, a second speech recognition dictionary from among the plurality of speech recognition dictionaries; and 
 generate a second speech recognition text using the second speech recognition dictionary by converting at least a part of the voices having been converted into the first speech recognition text using the first speech recognition dictionary. 
   
     
     
         14 . The information processing system according to  claim 13 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to convert a plurality of voices, uttered before the second speech recognition dictionary is selected, into the second speech recognition text, by speech recognition using the second speech recognition dictionary, to generate the second speech recognition text. 
     
     
         15 . The information processing system according to  claim 13 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to convert only voices uttered by the customer, into the second speech recognition text, among a plurality of voices uttered before the second speech recognition dictionary is selected, by speech recognition using the second speech recognition dictionary, to generate the second speech recognition text. 
     
     
         16 . The information processing system according to  claim 13 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to convert voices uttered after the second speech recognition dictionary is selected, into the second speech recognition text, by speech recognition using the second speech recognition dictionary, to generate the second speech recognition text. 
     
     
         17 . The information processing system according to  claim 13 , wherein the computer-executable program instructions further cause the information processing system to carry out the speech recognition only after a predetermined period of time elapses from a beginning of the voice call, and generate the speech recognition text using a predetermined speech recognition dictionary when no speech recognition dictionary is selected before the predetermined period of time elapses. 
     
     
         18 . The information processing system according to  claim 13 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to postpone the speech recognition on voices uttered before the second speech recognition dictionary is selected, for a predetermined period of time, depending on at least one of: a language of the voice call; content of a question; a subject matter of the voice call; and a product or technology to which the voice call is directed. 
     
     
         19 . An information processing system comprising:
 a processor; and   a memory storing computer-executable instructions that, when executed by the processor, cause the information processing system to at least:
 select a first speech recognition dictionary for use in speech recognition from among a plurality of speech recognition dictionaries; 
 generate first speech recognition text by converting voices uttered during a voice call with a customer, into the first speech recognition text, by speech recognition using the first speech recognition dictionary; 
 display the first speech recognition text on a screen; 
 select, subsequent to the selection of the first speech recognition dictionary, a second speech recognition dictionary, from among the plurality of speech recognition dictionaries; 
 generate second speech recognition text by converting voices uttered before the second speech recognition dictionary is selected and voices uttered after the second speech recognition dictionary is selected, among the voices uttered during the voice call with the customer, into the second speech recognition text, by speech recognition using the second speech recognition dictionary; and 
 display the second speech recognition text on the screen. 
   
     
     
         20 . The information processing system according to  claim 19 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to at least:
 divide the screen into a first screen and a second screen;   display, on the first screen, the second speech recognition text obtained by converting the voices uttered after the second speech recognition dictionary is selected, into the second speech recognition text, by the speech recognition using the second speech recognition dictionary; and   display, on the second screen, the first speech recognition text or the second speech recognition text obtained by converting the voices uttered before the second speech recognition dictionary is selected, into the second speech recognition text, by the speech recognition using the second speech recognition dictionary.   
     
     
         21 . The information processing system according to  claim 20 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the information processing system to display, on the first screen, the second speech recognition text, obtained by converting a latest voice uttered after the second speech recognition dictionary is selected, by the speech recognition using the second speech recognition dictionary. 
     
     
         22 . The information processing system according to  claim 20 , wherein, when the second speech recognition dictionary is selected, the computer-executable program instructions further cause the computer system to hide the second screen when the speech recognition is completed for the voices uttered before the second speech recognition dictionary is selected. 
     
     
         23 . An information processing method for causing a computer to perform steps including:
 selecting a first speech recognition dictionary for use in speech recognition from among a plurality of speech recognition dictionaries;   generating first speech recognition text by converting voices uttered during a voice call with a customer, into the first speech recognition text, by speech recognition using the first speech recognition dictionary; and   generating, upon a switchover from the first speech recognition dictionary to a second speech recognition dictionary, second speech recognition text by converting voices uttered before the switchover is made, among the voices uttered during the voice call with the customer, into the second speech recognition text, by speech recognition using the second speech recognition dictionary.   
     
     
         24 . A non-transitory computer-readable recording medium storing a program that, when executed by a computer, causes the computer to at least:
 select a first speech recognition dictionary for use in speech recognition from among a plurality of speech recognition dictionaries;   generate speech recognition text by converting voices uttered during a voice call with a customer, into text, by speech recognition using the first speech recognition dictionary; and   generate, upon a switchover from the first speech recognition dictionary to a second speech recognition dictionary, second speech recognition text by converting voices uttered before the switchover is made, among the voices uttered during the voice call with the customer, into the second speech recognition text, by speech recognition using the second speech recognition dictionary.